Method and device for calculating dense crowd flow based on video

A flow calculation and dense crowd technology, applied in the field of image processing, can solve problems such as manual intervention

Active Publication Date: 2020-01-31
SHANDONG NORMAL UNIV
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But in fact, many monitoring tasks undertaken by the current monitoring system still require manual intervention.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and device for calculating dense crowd flow based on video
  • Method and device for calculating dense crowd flow based on video
  • Method and device for calculating dense crowd flow based on video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] This embodiment provides a video-based dense crowd flow calculation method, such as figure 1 shown, including the following steps:

[0059] Step 1: Obtain a video sequence of a moving pedestrian target, and preprocess the acquired video sequence;

[0060] The video sequence can be acquired through the camera or added manually, and the video format can be avi, h.264 or mp4.

[0061] Step 2: Process video frames by frame difference to extract moving pedestrian targets;

[0062] Let the i-th frame of video use I i Indicates that the i+1th frame of video is represented by I i+1 Indicates that the i+2th frame of video is represented by I i+2 Indicates that the calculation of I i with I i+1 difference image of

[0063] Diff i = I i+1 -I i (1)

[0064] and I i+1 with I i+2 difference image of

[0065] Diff i+1 = I i+2 -I i+1 (2)

[0066] where Diff i means I i with I i+1 The difference image, Diff i+1 means I i+2 with I i+1 difference image.

[0067]...

Embodiment 2

[0103] Based on the calculation method for dense crowd flow provided by Embodiment 1, the present invention also provides another embodiment: a device for calculating dense crowd flow based on video, including:

[0104] A data acquisition module, configured to acquire a video sequence of a moving pedestrian target;

[0105] The target extraction module is used to process video frames through frame difference to extract moving pedestrian targets;

[0106] Region growing module for morphological processing of extracted pedestrian objects;

[0107] The number statistics module is used to obtain the movement trajectory of pedestrian targets, and count the pedestrian targets based on the movement trajectory.

[0108] Counting the pedestrian targets based on the motion trajectory in the number statistics module includes: for each pedestrian target, obtaining the moving distance of the target; calculating the moving direction of the pedestrian target; performing cross-border detecti...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a video-based dense crowd flow calculation method, comprising the following steps: Step 1: Acquiring video sequences of moving pedestrian targets; Step 2: Processing video frames through frame difference to extract moving pedestrian targets; Step 3: Perform morphological processing on the extracted pedestrian targets; Step 4: Obtain the trajectory of the pedestrian target, and count the pedestrian targets based on the trajectory; the calculation method of the present invention can realize real-time and accurate counting of dense crowds, and can adapt to various situations Under crowd detection and people counting.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a video-based calculation method for dense crowd flow. Background technique [0002] As early as the 1970s, video surveillance systems began to appear. Up to now, video surveillance systems have had a very important impact on society, and surveillance cameras are almost everywhere in the streets and alleys. But in fact, many monitoring tasks undertaken by the current monitoring system still require manual intervention. With the development of artificial intelligence technology, the intelligent monitoring system that has been emerging in recent years analyzes the collected video information through computer vision technology and pattern recognition technology, extracts useful information in the video and performs related operations, so that the existing The video surveillance system can automatically complete some video surveillance tasks without human intervention. [0003] Vide...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06T5/30G06T7/20
CPCG06T5/30G06T7/20G06T2207/30241G06T2207/30196G06T2207/10016G06V20/53
Inventor 万洪林白成杰李天平
Owner SHANDONG NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap